© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8316
    Prev
    Next
    INDEX
    Explanations

    report an accident, introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on tokens that begin a new paragraph or block of text—i.e. it marks paragraph‐start words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ficando
    0.87
     μέσα
    0.82
    ки
    0.80
     médias
    0.80
    吗
    0.80
    經歷
    0.77
     mágico
    0.75
    
    0.75
    lipid
    0.75
    燔
    0.74
    POSITIVE LOGITS
    ቖ
    0.73
    ari
    0.72
     LIABLE
    0.70
     chuck
    0.70
     Drucker
    0.67
    ΤΑ
    0.65
    ះ
    0.65
     beef
    0.64
     Eight
    0.64
     truc
    0.64
    Activations Density 0.000%

    No Known Activations